Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "173 patches.

  Subsystems affected by this series: ia64, ocfs2, block, and mm (debug,
  pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
  bootmem, sparsemem, vmalloc, kasan, pagealloc, memory-failure,
  hugetlb, userfaultfd, vmscan, compaction, mempolicy, memblock,
  oom-kill, migration, ksm, percpu, vmstat, and madvise)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (173 commits)
  mm/madvise: add MADV_WILLNEED to process_madvise()
  mm/vmstat: remove unneeded return value
  mm/vmstat: simplify the array size calculation
  mm/vmstat: correct some wrong comments
  mm/percpu,c: remove obsolete comments of pcpu_chunk_populated()
  selftests: vm: add COW time test for KSM pages
  selftests: vm: add KSM merging time test
  mm: KSM: fix data type
  selftests: vm: add KSM merging across nodes test
  selftests: vm: add KSM zero page merging test
  selftests: vm: add KSM unmerge test
  selftests: vm: add KSM merge test
  mm/migrate: correct kernel-doc notation
  mm: wire up syscall process_mrelease
  mm: introduce process_mrelease system call
  memblock: make memblock_find_in_range method private
  mm/mempolicy.c: use in_task() in mempolicy_slab_node()
  mm/mempolicy: unify the create() func for bind/interleave/prefer-many policies
  mm/mempolicy: advertise new MPOL_PREFERRED_MANY
  mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY
  ...

1 files changed, 101 insertions, 127 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 389b5766e74f..b762215d73eb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -103,6 +103,14 @@ static bool do_memsw_account(void)
 	return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_noswap;
 }
 
+/* memcg and lruvec stats flushing */
+static void flush_memcg_stats_dwork(struct work_struct *w);
+static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork);
+static void flush_memcg_stats_work(struct work_struct *w);
+static DECLARE_WORK(stats_flush_work, flush_memcg_stats_work);
+static DEFINE_PER_CPU(unsigned int, stats_flush_threshold);
+static DEFINE_SPINLOCK(stats_flush_lock);
+
 #define THRESHOLDS_EVENTS_TARGET 128
 #define SOFTLIMIT_EVENTS_TARGET 1024
 
@@ -248,9 +256,9 @@ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
 	return &memcg->vmpressure;
 }
 
-struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr)
+struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr)
 {
-	return &container_of(vmpr, struct mem_cgroup, vmpressure)->css;
+	return container_of(vmpr, struct mem_cgroup, vmpressure);
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -646,17 +654,6 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item. */
-static unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
-{
-	long x = READ_ONCE(memcg->vmstats.state[idx]);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
-
-/* idx can be of type enum memcg_stat_item or node_stat_item. */
 static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
 {
 	long x = 0;
@@ -671,23 +668,11 @@ static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
 	return x;
 }
 
-static struct mem_cgroup_per_node *
-parent_nodeinfo(struct mem_cgroup_per_node *pn, int nid)
-{
-	struct mem_cgroup *parent;
-
-	parent = parent_mem_cgroup(pn->memcg);
-	if (!parent)
-		return NULL;
-	return parent->nodeinfo[nid];
-}
-
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 			      int val)
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup *memcg;
-	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
@@ -696,21 +681,9 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__mod_memcg_state(memcg, idx, val);
 
 	/* Update lruvec */
-	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
-
-	if (vmstat_item_in_bytes(idx))
-		threshold <<= PAGE_SHIFT;
-
-	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
-	if (unlikely(abs(x) > threshold)) {
-		pg_data_t *pgdat = lruvec_pgdat(lruvec);
-		struct mem_cgroup_per_node *pi;
-
-		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
-			atomic_long_add(x, &pi->lruvec_stat[idx]);
-		x = 0;
-	}
-	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
+	__this_cpu_add(pn->lruvec_stats_percpu->state[idx], val);
+	if (!(__this_cpu_inc_return(stats_flush_threshold) % MEMCG_CHARGE_BATCH))
+		queue_work(system_unbound_wq, &stats_flush_work);
 }
 
 /**
@@ -905,7 +878,7 @@ EXPORT_SYMBOL(mem_cgroup_from_task);
 
 static __always_inline struct mem_cgroup *active_memcg(void)
 {
-	if (in_interrupt())
+	if (!in_task())
 		return this_cpu_read(int_active_memcg);
 	else
 		return current->active_memcg;
@@ -2205,8 +2178,9 @@ static void drain_local_stock(struct work_struct *dummy)
 	unsigned long flags;
 
 	/*
-	 * The only protection from memory hotplug vs. drain_stock races is
-	 * that we always operate on local CPU stock here with IRQ disabled
+	 * The only protection from cpu hotplug (memcg_hotplug_cpu_dead) vs.
+	 * drain_stock races is that we always operate on local CPU stock
+	 * here with IRQ disabled
 	 */
 	local_irq_save(flags);
 
@@ -2273,7 +2247,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 		if (memcg && stock->nr_pages &&
 		    mem_cgroup_is_descendant(memcg, root_memcg))
 			flush = true;
-		if (obj_stock_flush_required(stock, root_memcg))
+		else if (obj_stock_flush_required(stock, root_memcg))
 			flush = true;
 		rcu_read_unlock();
 
@@ -2289,40 +2263,13 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 	mutex_unlock(&percpu_charge_mutex);
 }
 
-static void memcg_flush_lruvec_page_state(struct mem_cgroup *memcg, int cpu)
-{
-	int nid;
-
-	for_each_node(nid) {
-		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
-		unsigned long stat[NR_VM_NODE_STAT_ITEMS];
-		struct batched_lruvec_stat *lstatc;
-		int i;
-
-		lstatc = per_cpu_ptr(pn->lruvec_stat_cpu, cpu);
-		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
-			stat[i] = lstatc->count[i];
-			lstatc->count[i] = 0;
-		}
-
-		do {
-			for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-				atomic_long_add(stat[i], &pn->lruvec_stat[i]);
-		} while ((pn = parent_nodeinfo(pn, nid)));
-	}
-}
-
 static int memcg_hotplug_cpu_dead(unsigned int cpu)
 {
 	struct memcg_stock_pcp *stock;
-	struct mem_cgroup *memcg;
 
 	stock = &per_cpu(memcg_stock, cpu);
 	drain_stock(stock);
 
-	for_each_mem_cgroup(memcg)
-		memcg_flush_lruvec_page_state(memcg, cpu);
-
 	return 0;
 }
 
@@ -4116,7 +4063,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	if (val > 100)
+	if (val > 200)
 		return -EINVAL;
 
 	if (!mem_cgroup_is_root(memcg))
@@ -4668,7 +4615,7 @@ void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
 		    atomic_read(&frn->done.cnt) == 1) {
 			frn->at = 0;
 			trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
-			cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0,
+			cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id,
 					       WB_REASON_FOREIGN_FLUSH,
 					       &frn->done);
 		}
@@ -4892,9 +4839,9 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 
 	vfs_poll(efile.file, &event->pt);
 
-	spin_lock(&memcg->event_list_lock);
+	spin_lock_irq(&memcg->event_list_lock);
 	list_add(&event->list, &memcg->event_list);
-	spin_unlock(&memcg->event_list_lock);
+	spin_unlock_irq(&memcg->event_list_lock);
 
 	fdput(cfile);
 	fdput(efile);
@@ -5129,17 +5076,9 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
-	pn->lruvec_stat_local = alloc_percpu_gfp(struct lruvec_stat,
-						 GFP_KERNEL_ACCOUNT);
-	if (!pn->lruvec_stat_local) {
-		kfree(pn);
-		return 1;
-	}
-
-	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct batched_lruvec_stat,
-					       GFP_KERNEL_ACCOUNT);
-	if (!pn->lruvec_stat_cpu) {
-		free_percpu(pn->lruvec_stat_local);
+	pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu,
+						   GFP_KERNEL_ACCOUNT);
+	if (!pn->lruvec_stats_percpu) {
 		kfree(pn);
 		return 1;
 	}
@@ -5160,8 +5099,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return;
 
-	free_percpu(pn->lruvec_stat_cpu);
-	free_percpu(pn->lruvec_stat_local);
+	free_percpu(pn->lruvec_stats_percpu);
 	kfree(pn);
 }
 
@@ -5177,15 +5115,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
 static void mem_cgroup_free(struct mem_cgroup *memcg)
 {
-	int cpu;
-
 	memcg_wb_domain_exit(memcg);
-	/*
-	 * Flush percpu lruvec stats to guarantee the value
-	 * correctness on parent's and all ancestor levels.
-	 */
-	for_each_online_cpu(cpu)
-		memcg_flush_lruvec_page_state(memcg, cpu);
 	__mem_cgroup_free(memcg);
 }
 
@@ -5321,6 +5251,10 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	/* Online state pins memcg ID, memcg ID pins CSS */
 	refcount_set(&memcg->id.ref, 1);
 	css_get(css);
+
+	if (unlikely(mem_cgroup_is_root(memcg)))
+		queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
+				   2UL*HZ);
 	return 0;
 }
 
@@ -5334,12 +5268,12 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	 * Notify userspace about cgroup removing only after rmdir of cgroup
 	 * directory to avoid race between userspace and kernelspace.
 	 */
-	spin_lock(&memcg->event_list_lock);
+	spin_lock_irq(&memcg->event_list_lock);
 	list_for_each_entry_safe(event, tmp, &memcg->event_list, list) {
 		list_del_init(&event->list);
 		schedule_work(&event->remove);
 	}
-	spin_unlock(&memcg->event_list_lock);
+	spin_unlock_irq(&memcg->event_list_lock);
 
 	page_counter_set_min(&memcg->memory, 0);
 	page_counter_set_low(&memcg->memory, 0);
@@ -5412,13 +5346,33 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 	memcg_wb_domain_size_changed(memcg);
 }
 
+void mem_cgroup_flush_stats(void)
+{
+	if (!spin_trylock(&stats_flush_lock))
+		return;
+
+	cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup);
+	spin_unlock(&stats_flush_lock);
+}
+
+static void flush_memcg_stats_dwork(struct work_struct *w)
+{
+	mem_cgroup_flush_stats();
+	queue_delayed_work(system_unbound_wq, &stats_flush_dwork, 2UL*HZ);
+}
+
+static void flush_memcg_stats_work(struct work_struct *w)
+{
+	mem_cgroup_flush_stats();
+}
+
 static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
 	struct memcg_vmstats_percpu *statc;
 	long delta, v;
-	int i;
+	int i, nid;
 
 	statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
 
@@ -5466,6 +5420,36 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 		if (parent)
 			parent->vmstats.events_pending[i] += delta;
 	}
+
+	for_each_node_state(nid, N_MEMORY) {
+		struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
+		struct mem_cgroup_per_node *ppn = NULL;
+		struct lruvec_stats_percpu *lstatc;
+
+		if (parent)
+			ppn = parent->nodeinfo[nid];
+
+		lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu);
+
+		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+			delta = pn->lruvec_stats.state_pending[i];
+			if (delta)
+				pn->lruvec_stats.state_pending[i] = 0;
+
+			v = READ_ONCE(lstatc->state[i]);
+			if (v != lstatc->state_prev[i]) {
+				delta += v - lstatc->state_prev[i];
+				lstatc->state_prev[i] = v;
+			}
+
+			if (!delta)
+				continue;
+
+			pn->lruvec_stats.state[i] += delta;
+			if (ppn)
+				ppn->lruvec_stats.state_pending[i] += delta;
+		}
+	}
 }
 
 #ifdef CONFIG_MMU
@@ -6399,6 +6383,8 @@ static int memory_numa_stat_show(struct seq_file *m, void *v)
 	int i;
 	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
+	cgroup_rstat_flush(memcg->css.cgroup);
+
 	for (i = 0; i < ARRAY_SIZE(memory_stats); i++) {
 		int nid;
 
@@ -6704,8 +6690,7 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root,
 			atomic_long_read(&parent->memory.children_low_usage)));
 }
 
-static int __mem_cgroup_charge(struct page *page, struct mem_cgroup *memcg,
-			       gfp_t gfp)
+static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp)
 {
 	unsigned int nr_pages = thp_nr_pages(page);
 	int ret;
@@ -6726,7 +6711,7 @@ out:
 }
 
 /**
- * mem_cgroup_charge - charge a newly allocated page to a cgroup
+ * __mem_cgroup_charge - charge a newly allocated page to a cgroup
  * @page: page to charge
  * @mm: mm context of the victim
  * @gfp_mask: reclaim mode
@@ -6739,16 +6724,14 @@ out:
  *
  * Returns 0 on success. Otherwise, an error code is returned.
  */
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
+int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
+			gfp_t gfp_mask)
 {
 	struct mem_cgroup *memcg;
 	int ret;
 
-	if (mem_cgroup_disabled())
-		return 0;
-
 	memcg = get_mem_cgroup_from_mm(mm);
-	ret = __mem_cgroup_charge(page, memcg, gfp_mask);
+	ret = charge_memcg(page, memcg, gfp_mask);
 	css_put(&memcg->css);
 
 	return ret;
@@ -6783,7 +6766,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
 		memcg = get_mem_cgroup_from_mm(mm);
 	rcu_read_unlock();
 
-	ret = __mem_cgroup_charge(page, memcg, gfp);
+	ret = charge_memcg(page, memcg, gfp);
 
 	css_put(&memcg->css);
 	return ret;
@@ -6919,18 +6902,15 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 }
 
 /**
- * mem_cgroup_uncharge - uncharge a page
+ * __mem_cgroup_uncharge - uncharge a page
  * @page: page to uncharge
  *
- * Uncharge a page previously charged with mem_cgroup_charge().
+ * Uncharge a page previously charged with __mem_cgroup_charge().
  */
-void mem_cgroup_uncharge(struct page *page)
+void __mem_cgroup_uncharge(struct page *page)
 {
 	struct uncharge_gather ug;
 
-	if (mem_cgroup_disabled())
-		return;
-
 	/* Don't touch page->lru of any random page, pre-check: */
 	if (!page_memcg(page))
 		return;
@@ -6941,20 +6921,17 @@ void mem_cgroup_uncharge(struct page *page)
 }
 
 /**
- * mem_cgroup_uncharge_list - uncharge a list of page
+ * __mem_cgroup_uncharge_list - uncharge a list of page
  * @page_list: list of pages to uncharge
  *
  * Uncharge a list of pages previously charged with
- * mem_cgroup_charge().
+ * __mem_cgroup_charge().
  */
-void mem_cgroup_uncharge_list(struct list_head *page_list)
+void __mem_cgroup_uncharge_list(struct list_head *page_list)
 {
 	struct uncharge_gather ug;
 	struct page *page;
 
-	if (mem_cgroup_disabled())
-		return;
-
 	uncharge_gather_clear(&ug);
 	list_for_each_entry(page, page_list, lru)
 		uncharge_page(page, &ug);
@@ -7244,7 +7221,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 }
 
 /**
- * mem_cgroup_try_charge_swap - try charging swap space for a page
+ * __mem_cgroup_try_charge_swap - try charging swap space for a page
  * @page: page being added to swap
  * @entry: swap entry to charge
  *
@@ -7252,16 +7229,13 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
  *
  * Returns 0 on success, -ENOMEM on failure.
  */
-int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 {
 	unsigned int nr_pages = thp_nr_pages(page);
 	struct page_counter *counter;
 	struct mem_cgroup *memcg;
 	unsigned short oldid;
 
-	if (mem_cgroup_disabled())
-		return 0;
-
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return 0;
 
@@ -7297,11 +7271,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 }
 
 /**
- * mem_cgroup_uncharge_swap - uncharge swap space
+ * __mem_cgroup_uncharge_swap - uncharge swap space
  * @entry: swap entry to uncharge
  * @nr_pages: the amount of swap space to uncharge
  */
-void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
+void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
 {
 	struct mem_cgroup *memcg;
 	unsigned short id;